home / skills / fluxa-agent-payment / skills / my-skill

my-skill skill

/skills/my-skill

This skill orchestrates Grok, VEO 3.1 video generation, OpenAI endpoints, and Kling I2V to streamline multimedia automation.

npx playbooks add skill fluxa-agent-payment/skills --skill my-skill

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.1 KB
---
name: my-skill
description: A skill that uses Grok API call, Video Generation with VEO 3.1, OpenAI API Endpoints, KLing I2V
---

# My Skill

This skill uses the following paid APIs:
- **Grok API call**: API for calling grok
- **Video Generation with VEO 3.1**: Using Google's veo 3.1 to generate videos
- **OpenAI API Endpoints**: APIs for OpenAI models
- **KLing I2V**: API for creating video from image

## What This Skill Does

<!-- Describe what your skill does here -->

## Usage

<!-- Describe how to use this skill -->

## tools

* Grok API call

  * name: pay-per-use-based grok-api-call
  * access: agent-pay
  * usage:
    ```
    ** API Discovery ** First, discover available endpoints by making a GET request to the base URL:
    curl https://proxy.fluxapay.xyz/api/grok-api-call
    ```

* Video Generation with VEO 3.1

  * name: pay-per-use-based video-generation-with-veo-3-1
  * access: agent-pay
  * usage:
    ```
    ** API Discovery ** First, discover available endpoints by making a GET request to the base URL:
    curl https://proxy.fluxapay.xyz/api/video-generation-with-veo-3-1
    ```

* OpenAI API Endpoints

  * name: pay-per-use-based openai-api-endpoints
  * access: agent-pay
  * usage:
    ```
    ** API Discovery ** First, discover available endpoints by making a GET request to the base URL:
    curl https://proxy.fluxapay.xyz/api/openai-api-endpoints
    ```

* KLing I2V

  * name: pay-per-use-based kling-i2v
  * access: agent-pay
  * usage:
    ```
    ** API Discovery ** First, discover available endpoints by making a GET request to the base URL:
    curl https://proxy.fluxapay.xyz/api/kling-i2v
    ```

* Make X402 payment: see ./fluxa-wallet/X402-PAYMENT.md


# notes for tools use

* If the invoked tool's access is **agent-pay**, it means the tool is accessed by the agent on a **pay-per-use** basis.
  The agent needs to handle x402 payment flow to use these tools.
  See ./fluxa-wallet/SKILL.md for the complete payment wallet documentation.
* For x402 payment details, refer to ./fluxa-wallet/X402-PAYMENT.md
* For payout operations, refer to ./fluxa-wallet/PAYOUT.md
* For payment link operations, refer to ./fluxa-wallet/PAYMENT-LINK.md

Overview

This skill integrates multiple paid APIs to analyze content and generate video assets programmatically. It combines Grok for advanced inspection, VEO 3.1 and KLing I2V for video creation, and OpenAI API endpoints for text and multimodal processing. The agent accesses these tools on a pay-per-use basis and requires a payment flow before calls succeed.

How this skill works

The skill discovers available API endpoints and then routes requests to the appropriate provider: Grok for content analysis and extraction, OpenAI endpoints for text generation or model inference, VEO 3.1 for high-level video generation from prompts, and KLing I2V to convert images into short videos. Each tool is accessed via agent-pay, so the agent triggers a payment flow (x402) and then calls the selected endpoint to receive responses or generated assets.

When to use it

  • Generate marketing or social videos from text prompts or images
  • Automate multimedia content creation in pipelines or apps
  • Augment chatbots with generated video or image-to-video outputs
  • Analyze text, transcripts, or media metadata with Grok before generation
  • Prototype cross-model workflows combining OpenAI outputs with video generation

Best practices

  • Discover and test endpoints before production to confirm available parameters and limits
  • Implement the required pay-per-use payment flow and track spending per call
  • Validate and sanitize prompts and inputs to avoid unexpected results or unsafe content
  • Use retries, timeouts, and error handling for network and API failures
  • Limit output lengths, video durations, and asset sizes to control cost and processing time

Example use cases

  • Create short promotional videos from a product description using VEO 3.1
  • Transform a product image into a looping demo clip with KLing I2V
  • Run Grok analysis on user uploads to extract tags, timestamps, or safety signals before publishing
  • Use OpenAI endpoints to draft narration, scripts, or captions, then generate a finished video
  • Build an automated pipeline that accepts content, analyzes intent, generates a script, and produces a video asset

FAQ

Do I need to pay before using the tools?

Yes. Each tool is agent-pay (pay-per-use). The agent must complete the required payment flow for calls to proceed and will bill according to usage.

How do I discover available endpoints and parameters?

Call the tool base URL with a discovery GET request to list endpoints and supported parameters before making production requests.

What inputs are supported for video generation?

VEO 3.1 accepts text prompts and generation parameters; KLing I2V accepts images as input for image-to-video conversion. Use OpenAI endpoints for script and narration generation.